استفاده از الگوریتم ماشین بردار پشتیبان برای پیش بیني بیماری عروق کرونر قلب در زنان میانسال فعال (Persian).

Using Support Vector Machine Algorithm to Predict Coronary Heart Disease in Active Middle-aged Women. (English)

SUPPORT vector machines; ANTHROPOMETRY; CORONARY disease; COMPARATIVE studies; PHYSICAL activity; PREVENTIVE health services; DESCRIPTIVE statistics; PREDICTION models; SENSITIVITY & specificity (Statistics); DATA analysis software; ROUTINE diagnostic tests; ANGIOGRAPHY; ALGORITHMS; MIDDLE age

Background and Aim: Coronary artery disease is the most common form of cardiovascular disease, and it frequently causes myocardial infarction. It causes billions of dollars in property damage and millions of deaths worldwide every year. The standard method for diagnosing cardiovascular disease is angiography, which is invasive and dangerous. A machine learning system has been widely used as a fast, cost-effective, and noninvasive approach to the diagnosis of cardiovascular disease. Therefore, the purpose of this research was to use a support vector machine algorithm to predict coronary heart disease in active middle-aged women. Methods: In this study, the medical records of 372 middle-aged women with coronary artery disease who were hospitalized in two selected hospitals during 2015-2016 were used. A support vector machine algorithm was used to diagnose coronary artery disease. MATLAB software was used for data analysis at a significance level of 0.05. Results: The results showed that by using medical records containing 14 common features, related to anthropometric information, diagnostic tests, angiography results, and physical activity, the support vector machine algorithm can detect vascular diseases with 70% accuracy and 76% precision. Conclusion: The use of a machine learning approach provides the ability to predict the presence of coronary artery disease with high accuracy and sensitivity. Therefore, it allows doctors to provide timely preventive treatment in patients with coronary artery disease. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Military Medicine is the property of Baqiyatallah University of Medical Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)